Querying Service Metadata

Function

Queries service metadata.

This API is scheduled for deprecation.

Format

Operation type: GET

URL: https://{ip}:{port}/v2

Replace {ip} and {port} with the IP address and port number of the service plane, that is, ipAddress and port.

Request Parameters

None

Usage Example

Request example:

GET https://{ip}:{port}/v2

Response example:

{
    "name": "MindIE Server",
    "version": "{version}",
    "extensions": {
        "max_iter_times": 512,  
        "prefill_policy_type": 0,
        "decode_policy_type": 0,
        "max_prefill_batch_size": 50,
        "max_prefill_tokens": 8192
    }
}

Response status code: 200

Output Description

Parameter	Type	Description
name	String	Service name. Currently, the value is MindIE Server.
version	String	Service version.
extensions	Object	Extended field.
max_iter_times	Integer	Maximum number of decode times.
prefill_policy_type	Integer	Scheduling policy in the prefill phase. For details, see prefillPolicyType in Parameters in ScheduleConfig.
decode_policy_type	Integer	Scheduling policy in the decode phase. For details, see decodePolicyType in Parameters in ScheduleConfig.
max_prefill_batch_size	Integer	Maximum prefill batch size.
max_prefill_tokens	Integer	Maximum number of prefill tokens.

Parent topic: APIs Compatible with Triton